ETRI-Knowledge Sharing Plaform



논문 검색
구분 SCI
연도 ~ 키워드


학술대회 Object Recognition and Pose Estimation for Modular Manipulation System: Overview and Initial Results
Cited 5 time in scopus Download 3 time Share share facebook twitter linkedin kakaostory
윤우한, 이재연, 이주행, 김재홍
International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) 2017, pp.198-201
16PS2200, 로봇 적용 범위 확장을 위해 3종의 조인트 모듈, 최대 7자유도의 기구부 조합에 따른 제어, 인지 시스템의 자동 구성이 가능한 모듈라 매니퓰레이션 기술 개발, 김재홍
Object detection and pose estimation is a fundamental functionality among robotic perception for manipulation. Applying robots to diverse tasks requires a robust perception skill. In this manuscript, we introduce an overview of our object recognition and pose estimation process and its our initial results. Our approach follows the previous approaches using local feature extraction and match. As a training stage, synthetic dataset is generated with its 2D-3D information. Local features is extracted and its 2D-3D information are stored in the dataset. As a test stage, the background area is removed and blobs which might include object candidates are extracted. Then, the local features are extracted and matched with the features stored in the database and the correspondences are found. Based on the correspondences, object instance and pose information is estimated by solving Perspective-n-Point problem. To validate our approach, we trained the system with synthetic images and tested it with real images for object recognition and detection and with synthetic images for object pose estimation.
KSP 제안 키워드
2D-3D, 3D information, Local feature extraction, Manipulation system, Object Candidates, Object Pose Estimation, Object Recognition, Object detection, Perspective-n-point problem, Robotic perception, Synthetic Datasets